CN117218097B - Method and device for detecting surface defects of shaft sleeve type silk screen gasket part - Google Patents
Method and device for detecting surface defects of shaft sleeve type silk screen gasket part Download PDFInfo
- Publication number
- CN117218097B CN117218097B CN202311234126.0A CN202311234126A CN117218097B CN 117218097 B CN117218097 B CN 117218097B CN 202311234126 A CN202311234126 A CN 202311234126A CN 117218097 B CN117218097 B CN 117218097B
- Authority
- CN
- China
- Prior art keywords
- image information
- shaft sleeve
- sleeve type
- image
- defect
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000007547 defect Effects 0.000 title claims abstract description 163
- 238000000034 method Methods 0.000 title claims abstract description 84
- 238000001514 detection method Methods 0.000 claims abstract description 96
- 238000007781 pre-processing Methods 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims description 52
- 238000001914 filtration Methods 0.000 claims description 30
- 230000008569 process Effects 0.000 claims description 17
- 238000004422 calculation algorithm Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000000354 decomposition reaction Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 10
- 230000004927 fusion Effects 0.000 claims description 10
- 230000009466 transformation Effects 0.000 claims description 9
- 230000009467 reduction Effects 0.000 claims description 8
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 6
- 238000012856 packing Methods 0.000 claims description 2
- 230000002950 deficient Effects 0.000 description 10
- 238000004891 communication Methods 0.000 description 9
- 238000012549 training Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 6
- 238000012360 testing method Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 238000003066 decision tree Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000013145 classification model Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 229910001369 Brass Inorganic materials 0.000 description 1
- 229910000906 Bronze Inorganic materials 0.000 description 1
- 229910001018 Cast iron Inorganic materials 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000010951 brass Substances 0.000 description 1
- 239000010974 bronze Substances 0.000 description 1
- -1 burrs Substances 0.000 description 1
- KUNSUQLRTQLHQQ-UHFFFAOYSA-N copper tin Chemical compound [Cu].[Sn] KUNSUQLRTQLHQQ-UHFFFAOYSA-N 0.000 description 1
- 238000013016 damping Methods 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 230000001627 detrimental effect Effects 0.000 description 1
- 239000002828 fuel tank Substances 0.000 description 1
- 238000000227 grinding Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Image Analysis (AREA)
Abstract
The invention provides a method and a device for detecting surface defects of a shaft sleeve type silk screen gasket part, which relate to the technical field of detection of surface defects of the shaft sleeve type silk screen gasket part and comprise the steps of acquiring an image information set of the shaft sleeve type silk screen gasket to be detected; preprocessing the image information set, and extracting texture features of the preprocessed image information set to obtain part image defect features; constructing a shaft sleeve type silk screen gasket part defect detection model by utilizing the part image defect characteristics; and identifying the image information set of the shaft sleeve type wire mesh gasket to be detected according to the defect detection model of the shaft sleeve type wire mesh gasket part to be detected, and identifying to obtain the surface defect of the shaft sleeve type wire mesh gasket part to be detected. The invention not only reduces the labor cost, but also improves the detection efficiency of the defects of the parts, reduces the false detection rate and the omission rate of the defects of the parts, and further improves the detection accuracy of the defects of the parts.
Description
Technical Field
The invention relates to the technical field of detection of surface defects of parts of shaft sleeve type silk screen gaskets, in particular to a method and a device for detecting the surface defects of the parts of the shaft sleeve type silk screen gaskets.
Background
With the deep integration of new generation information technology and manufacturing industry, the manufacturing industry is caused to generate great revolution, and the transition from the quantity amplification to the quality improvement is gradually carried out. The product quality is improved to produce the product with high added value and high profit, and the jump of the product competitiveness can be realized. Industrial part surface defects not only destroy the aesthetic feeling and comfort of the product, but can also cause serious damage to the performance of the product.
The shaft sleeve type silk screen gasket part mainly plays roles of supporting, guiding, positioning and the like, has extremely wide application in various machines and instruments, and is generally manufactured by selecting materials such as steel, cast iron, bronze or brass. During the production, handling, assembly and the like of the silk screen gasket part, various grinding marks can be generated on the surface, the end face and the like of the silk screen gasket part to cause defects such as unevenness, pits, bias and the like. These defects will have a detrimental effect on the service performance of the part and affect the accuracy of the revolution, vibration, noise, sealing and service life of the whole machine. In the prior art, the traditional manual spot check is generally adopted to detect the surface defects of the product, but the detection is easy to be carried out by the manual detection, errors are caused by subjective factors, the detection is easy to be carried out, the quality of industrial parts is easy to miss, the safety accidents are seriously caused, the accuracy of the existing detection method is low, and the model training and recognition speed is relatively low, so that the requirement of modern enterprises on improving the quality of the product cannot be met.
Disclosure of Invention
The invention aims to provide a method and a device for detecting surface defects of parts of shaft sleeve type silk screen gaskets, so as to solve the problems. In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
in a first aspect, the present application provides a method for detecting a surface defect of a wire mesh gasket part of a shaft sleeve, including:
acquiring an image information set of a to-be-detected shaft sleeve type wire mesh gasket, wherein the image information set comprises first image information of the inner surface and second image information of the outer surface of the to-be-detected shaft sleeve type wire mesh gasket, and the first image information and the second image information comprise damage information;
preprocessing the image information set, and extracting texture features of the preprocessed image information set to obtain part image defect features;
constructing a shaft sleeve type silk screen gasket part defect detection model by utilizing the part image defect characteristics;
and identifying the image information set of the shaft sleeve type wire mesh gasket to be detected according to the defect detection model of the shaft sleeve type wire mesh gasket part to be detected, and identifying to obtain the surface defect of the shaft sleeve type wire mesh gasket part to be detected.
Preferably, the preprocessing the image information set includes:
and carrying out Gaussian noise processing on the image information set by using a Gaussian filtering algorithm to obtain first processed image information, wherein the calculation formula is as follows:
wherein N is i Representing an image information set, I representing a denoising factor, H representing a gaussian filter, σ representing a filtering process average variance, M i Representing first processed image information, T representing time;
normalizing the first processed image information to obtain second processed image information;
and carrying out background reconstruction on the second processed image information by using a polynomial curved surface fitting method to obtain third processed image information, and recording the third processed image information as a preprocessed image information set.
Preferably, the third processing unit performs a specific process of performing background reconstruction on the target image information by using a polynomial curved surface fitting method, where the specific process is as follows:
I(x,y)＝a 00 +a 10 x+a 01 y+a 20 x 2 +a 02 y 2 +a 30 x 3 +a 03 y 3 +b
in the above formula, I (x, y) is pixel data for reconstructing a background, x, y is coordinate values of pixels for reconstructing a background image, b is an error term, and a00 and a10 … … a03 are coefficients corresponding to polynomials, respectively; and extracting the characteristics of the third processed image information to obtain a characteristic extracted image, and recording the characteristic extracted image as a preprocessed image information set.
Preferably, the extracting texture features of the preprocessed image information set to obtain part image defect features includes:
carrying out data enhancement processing on the preprocessed image information set to obtain enhanced image information, wherein the data enhancement processing process comprises the steps of manually generating a defect image, affine transformation and color dithering;
performing median filtering processing on the enhanced image information to obtain three-dimensional gray image information for removing distortion parts in the enhanced image information;
selecting at least two texture features to calculate the three-dimensional gray image information to obtain feature image information, wherein the texture features comprise roughness, contrast and direction degree;
and reducing the dimension of the characteristic image information by using PCA to obtain the defect characteristic of the part image.
Preferably, the step of constructing a part defect detection model of the shaft sleeve type wire mesh gasket by using the part image defect characteristics comprises the following steps:
obtaining a multiscale decomposition function of the part image of the shaft sleeve type silk screen gasket according to the part image defect characteristics and the tracking and positioning of the image characteristics;
obtaining a fusion filtering correlation coefficient of the shaft sleeve type silk screen gasket part image by adopting a characteristic weight analysis method;
based on the scale decomposition function and the fusion filtering correlation coefficient, adopting an image super-resolution characteristic reconstruction algorithm to dynamically detect the image of the shaft sleeve type wire mesh gasket part to obtain the polygonal contour characteristic detection frequency of the shaft sleeve type wire mesh gasket part;
and obtaining texture components according to the polygonal contour feature detection frequency, and further obtaining the defect detection model of the shaft sleeve type silk screen gasket part through the texture components.
In a second aspect, the application further provides a device for detecting surface defects of a part of a wire mesh gasket of a shaft sleeve, which comprises an acquisition module, a preprocessing module, a construction module and an identification module, wherein:
the acquisition module is used for: the method comprises the steps of acquiring an image information set of a to-be-detected shaft sleeve type wire mesh gasket, wherein the image information set comprises first image information of the inner surface and second image information of the outer surface of the to-be-detected shaft sleeve type wire mesh gasket, and the first image information and the second image information comprise damage information;
and a pretreatment module: the method comprises the steps of preprocessing an image information set, and extracting texture features of the preprocessed image information set to obtain part image defect features;
the construction module comprises: the method is used for constructing a shaft sleeve type silk screen gasket part defect detection model by utilizing the part image defect characteristics;
and an identification module: and the method is used for identifying the image information set of the shaft sleeve type wire mesh gasket to be detected according to the defect detection model of the shaft sleeve type wire mesh gasket part to be detected, and identifying to obtain the surface defect of the shaft sleeve type wire mesh gasket part to be detected.
In a third aspect, the present application further provides a device for detecting surface defects of a wire mesh gasket part of a shaft sleeve, including:
a memory for storing a computer program;
and the processor is used for realizing the step of the method for detecting the surface defects of the shaft sleeve type wire mesh gasket part when executing the computer program.
In a fourth aspect, the present application further provides a readable storage medium, where a computer program is stored, where the computer program when executed by a processor implements the steps of the method for detecting surface defects of parts based on a wire mesh gasket of a shaft sleeve.
The beneficial effects of the invention are as follows:
the invention adopts Gaussian filter algorithm and normalization processing, which can eliminate the interference of various factors suffered by the image in the industrial environment, and in order to avoid the influence of image noise and shadow on the subsequent extraction and defect detection of potential defect areas, gaussian filter denoising and image pretreatment are required to be carried out on the acquired surface image of the part; the problem of deficiency of a defect image database is solved through data enhancement, and the manual generation of the defect image refers to simulating a defective part and converting a normal image into a defective image; affine transformation refers to a linear transformation of a vector space followed by a translation to transform it into another vector space. Data enhancement is used to increase the number of defective samples and to increase the robustness of the network; feature dimension reduction is carried out through PCA, and different from the single extraction histogram in the traditional texture detection method, feature parameters are reasonably selected according to defect types, and different parameters are selected according to surface defects of different study objects, so that the accuracy of detection results can be effectively improved; the invention ensures the authenticity and reliability of the acquired image, realizes autonomy and intelligence of product detection according to the acquired image, improves detection precision and detection efficiency, promotes further development of product quality monitoring technology, acquires specific parameters by constructing a shaft sleeve type silk screen gasket part defect detection model, and performs data identification matching on various and personalized products, thereby improving production efficiency. The whole detection process does not need to be manually participated, so that the labor cost is reduced, and the detection efficiency of the defects of the parts of the wire mesh gaskets of the shaft sleeves is improved. And the defects of the parts are detected together by adopting an image super-resolution characteristic reconstruction algorithm and a defect detection model, so that the false detection rate and the omission rate of the defects of the parts of the wire mesh gaskets of the shaft sleeves are reduced, and the detection accuracy of the defects of the parts of the wire mesh gaskets of the shaft sleeves is further improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the embodiments of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for detecting surface defects of a part of a wire mesh gasket of a shaft sleeve type according to an embodiment of the invention;
FIG. 2 is a schematic diagram of a device for detecting surface defects of a wire mesh gasket part of a shaft sleeve according to an embodiment of the invention;
fig. 3 is a schematic structural diagram of a device for detecting surface defects of a wire mesh gasket part of a shaft sleeve according to an embodiment of the invention.
In the figure: 701. an acquisition module; 702. a preprocessing module; 7021. a first processing unit; 7022. a second processing unit; 7023. a third processing unit; 7024. a fourth processing unit; 7025. a fifth processing unit; 7026. a calculation unit; 7027. a dimension reduction unit; 703. constructing a module; 7031. a first obtaining unit; 7032. a second obtaining unit; 7033. a detection unit; 7034. a third obtaining unit; 704. an identification module; 7041. splitting the unit; 7042. a fourth obtaining unit; 7043. an identification unit; 800. the surface defect detection equipment of the shaft sleeve type silk screen gasket part; 801. a processor; 802. a memory; 803. a multimedia component; 804. an I/O interface; 805. a communication component.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
Example 1:
the embodiment provides a method for detecting surface defects of parts of shaft sleeve type silk screen gaskets.
Referring to fig. 1, the method is shown to include step S100, step S200, step S300, and step S400.
S100, acquiring an image information set of the to-be-detected shaft sleeve type wire mesh gasket, wherein the image information set comprises first image information of the inner surface and second image information of the outer surface of the to-be-detected shaft sleeve type wire mesh gasket, and the first image information and the second image information comprise damage information.
It will be appreciated that in this step, the camera starts to capture images after receiving the trigger signal. Imaging principle of industrial camera: the industrial lens refracts the light reflected by the measured object to the photosensitive sensor to generate an analog current signal, and the analog current signal cannot be directly recognized by the computer, so that the signal is converted into a digital signal through the A/D module and is transmitted to the image processor, and finally, the digital signal is transmitted to the computer through the communication interface. Based on the principle of nondestructive detection, an endoscopic lens is used, the inner wall is unfolded to be similar to a plane image, and defects such as impurities, burrs, sand holes and the like are identified. The axle sleeve type silk screen packing ring part can be adopted to set up in the middle, erects 4 cameras respectively in the side and carries out the side shooting, specifically, in the vision module, 4 cameras encircle the installation, every camera shoots the area of bearing side 1/4 when shooing, every camera is at bearing motion in-process simultaneously from A (a certain fixed point) beginning shooting, to the B point end, and the camera is "continuously" shooing after receiving trigger signal during the period, sets up camera frame rate according to the picture volume that needs to shoot. Because the camera adopts a frame triggering mode to collect images, the frame rate means the number of images collected per second. The calculation formula is as follows, wherein X is the picture quantity, d is the bearing diameter, fov is the field size, and the frame rate is X/s:
s200, preprocessing the image information set, and extracting texture features of the preprocessed image information set to obtain part image defect features.
It will be appreciated that the present step S200 includes steps S201, S202 and S203, wherein:
s201, gaussian noise processing is carried out on the image information set by utilizing a Gaussian filtering algorithm, first processed image information is obtained, and a calculation formula is as follows:
wherein N is i Representing an image information set, I representing a denoising factor, H representing a gaussian filter, σ representing a filtering process average variance, M i Representing first processed image information, T representing time;
s202, carrying out normalization processing on the first processed image information to obtain second processed image information;
it should be noted that, the interference of various factors suffered by the image in the industrial environment can be eliminated by adopting the gaussian filtering algorithm and the normalization processing, and in order to avoid the influence of image noise and shadow on the subsequent extraction of the potential defect area and the defect detection, the collected surface image of the part needs to be subjected to gaussian filtering denoising and image preprocessing.
S203, performing background reconstruction on the second processed image information by using a polynomial curved surface fitting method to obtain third processed image information, and recording the third processed image information as a preprocessed image information set.
The specific process of background reconstruction of the target image information by using the polynomial curved surface fitting method is as follows:
I(x,y)＝a 00 +a 10 x+a 01 y+a 20 x 2 +a 02 y 2 +a 30 x 3 +a 03 y 3 +b
in the above expression, I (x, y) is pixel data for reconstructing a background, x, y is coordinate values of pixels for reconstructing a background image, b is an error term, and a00 and a10 … … a03 are coefficients corresponding to polynomials, respectively. And extracting the characteristics of the third processed image information to obtain a characteristic extracted image, and recording the characteristic extracted image as a preprocessed image information set.
In this step, the contour feature of the surface defect of the part can be effectively extracted by performing image segmentation on the third processed image information, so as to realize automatic detection of the surface defect of the part.
It will be appreciated that the present step S200 further includes S204, S205, S206 and S207, wherein:
s204, carrying out data enhancement processing on the preprocessed image information set to obtain enhanced image information, wherein the data enhancement processing process comprises the steps of manually generating a defect image, affine transformation and color dithering;
it should be noted that, the problem of lack of the defect image database is solved by data enhancement, and the manual generation of the defect image refers to simulating a defective part and converting a normal image into a defective image; affine transformation refers to a linear transformation of a vector space followed by a translation to transform it into another vector space. Data enhancement is used to increase the number of defective samples and to increase the robustness of the network.
S205, performing median filtering processing on the enhanced image information to obtain three-dimensional gray image information for removing distortion parts in the enhanced image information;
it will be appreciated that the use of a median filtering process may reduce noise reduction.
S206, selecting at least two texture features to calculate the three-dimensional gray image information to obtain feature image information, wherein the texture features comprise roughness, contrast and direction degree;
s207, reducing the dimension of the feature image information by utilizing PCA to obtain the defect feature of the part image.
It can be understood that feature dimension reduction is performed by PCA, which is different from the single extraction histogram in the traditional texture detection method, but the feature parameters are reasonably selected according to the defect types, and different parameters are selected according to the surface defects of different study objects, so that the accuracy of the detection result can be effectively improved.
S300, constructing a shaft sleeve type silk screen gasket part defect detection model by utilizing the part image defect characteristics.
It will be appreciated that the present step S300 includes steps S301, S302, S303 and S304, wherein:
s301, obtaining a multiscale decomposition function of the part image of the shaft sleeve type silk screen gasket according to the part image defect characteristics and the tracking and positioning of the image characteristics;
s302, obtaining a fusion filtering correlation coefficient of the shaft sleeve type silk screen gasket part image by adopting a characteristic weight analysis method;
s303, dynamically detecting the image of the shaft sleeve type silk screen gasket part by adopting an image super-resolution characteristic reconstruction algorithm based on the scale decomposition function and the fusion filtering correlation coefficient to obtain the polygonal contour characteristic detection frequency of the shaft sleeve type silk screen gasket part;
it can be appreciated that the calculation formula is as follows:
in the method, in the process of the invention,σ 1 the frequencies are reconstructed for the pixel features.
S304, obtaining texture components according to the polygonal contour feature detection frequency, and further obtaining the defect detection model of the shaft sleeve type silk screen gasket part through the texture components.
It can be understood that the method guarantees the authenticity and reliability of the acquired image, realizes autonomy and intelligence of product detection according to the acquired image and corresponding analysis result, improves detection precision and detection efficiency, promotes further development of product quality monitoring technology, acquires specific parameters by constructing a shaft sleeve type silk screen gasket part defect detection model, and performs data identification matching on various and personalized products, thereby improving production efficiency.
And S400, identifying the image information set of the shaft sleeve type wire mesh gasket to be detected according to the defect detection model of the shaft sleeve type wire mesh gasket part, and identifying to obtain the surface defect of the shaft sleeve type wire mesh gasket part to be detected.
It will be appreciated that the present step S400 includes steps S401, S402 and S403, wherein:
s401, splitting unit: the image information set of the to-be-detected shaft sleeve type wire mesh gasket is divided into a training set and a testing set based on the defect detection model of the shaft sleeve type wire mesh gasket part, wherein the training set is a defect area characteristic vector of the shaft sleeve type wire mesh gasket part, and the testing set is a damage area characteristic vector of the shaft sleeve type wire mesh gasket part;
s402, a fourth obtaining unit: the method comprises the steps of inputting the training set and the testing set into a defect detection model of the shaft sleeve type silk screen gasket part to obtain a first identification result;
s403, an identification unit: and training a classification model by using the C4.5 decision tree and the first recognition result, and recognizing to obtain the surface defect of the to-be-detected shaft sleeve type silk screen gasket part.
It is to be understood that based on the true defect detection of the decision tree, the authenticity and reliability of the defect detection of the shaft sleeve type wire mesh gasket part are improved. Although the curve does not have regular texture information in the class, defects such as dishing, unevenness, bias voltage and the like generally have irregular gray scale variation in the region, so that gray scale classification can be described through a decision tree, differences among classes are described, differences between damage and defects are exposed, and accuracy of defect detection is improved.
Specifically, in this embodiment, a wire mesh gasket is taken as an example, where the wire mesh gasket is a spare part for a vehicle fuel tank interface, and has the functions of fixing, preventing leakage and damping, and is adapted to the shaft sleeve, but because the wire mesh gasket is mainly made of metal, the surface is smoother. However, under the irradiation of the light source, the image of the surface of the non-defective measured object presents uniform gray scale, color and texture without abrupt change, and the surface with defects has abrupt change, which can be used as the basis for judging the defects. Generally, because defects such as pits, unevenness, bias and the like can present different image characteristics under different light sources, illumination modes and image acquisition modes, firstly, an image information set of a shaft sleeve type silk screen gasket to be detected needs to be acquired, and shaft sleeve type parts can be used for establishing a defect sample library, namely the image information set; in order to eliminate the interference of various factors suffered by the image in the industrial environment and avoid the influence of image noise and shadow on the subsequent extraction of potential defect areas and defect detection, gaussian filtering denoising and image preprocessing are required to be carried out on the acquired surface image of the part, so that relatively clear texture characteristic image characteristics can be obtained; then, a defect detection model can be constructed according to relatively clear texture feature image features, further, the constructed defect detection model can be utilized to carry out defect identification on image data of each silk screen gasket to be identified, the defect position of the silk screen gasket can be detected after identification, wherein whether defects such as various depressions, unevenness and bias voltages exist on the surface, the end face and the like of the silk screen gasket or not can be judged, different parameters are selected according to the surface defects of different research objects, the accuracy, the detection precision and the detection efficiency of detecting the surface defects of the silk screen gasket can be effectively improved, the processing time is greatly shortened, the online detection is realized, the online detection is better matched with a shaft sleeve, and the vehicle oil tank is prevented from being permeated.
Example 2:
as shown in fig. 2, the embodiment provides a device for detecting surface defects of a wire mesh gasket part of a shaft sleeve, and the device described with reference to fig. 2 includes an acquisition module 701, a preprocessing module 702, a construction module 703 and an identification module 704, wherein:
the acquisition module 701: the method comprises the steps of acquiring an image information set of a to-be-detected shaft sleeve type wire mesh gasket, wherein the image information set comprises first image information of the inner surface and second image information of the outer surface of the to-be-detected shaft sleeve type wire mesh gasket, and the first image information and the second image information comprise damage information;
preprocessing module 702: the method comprises the steps of preprocessing an image information set, and extracting texture features of the preprocessed image information set to obtain part image defect features;
the construction module 703: the method is used for constructing a shaft sleeve type silk screen gasket part defect detection model by utilizing the part image defect characteristics;
the identification module 704: and the method is used for identifying the image information set of the shaft sleeve type wire mesh gasket to be detected according to the defect detection model of the shaft sleeve type wire mesh gasket part to be detected, and identifying to obtain the surface defect of the shaft sleeve type wire mesh gasket part to be detected.
Specifically, the preprocessing module 702 includes a first processing unit 7021, a second processing unit 7022, and a third processing unit 7023, wherein:
first processing unit 7021: the method is used for carrying out Gaussian noise processing on the image information set by utilizing a Gaussian filtering algorithm to obtain first processed image information, and the calculation formula is as follows:
wherein N is i Representing an image information set, I representing a denoising factor, H representing a gaussian filter, σ representing a filtering process average variance, M i Representing first processed image information, T representing time;
second processing unit 7022: the normalization processing is used for carrying out normalization processing on the first processed image information to obtain second processed image information;
third processing unit 7023: and the method is used for carrying out background reconstruction on the second processed image information by using a polynomial curved surface fitting method to obtain third processed image information, and the third processed image information is recorded as a preprocessed image information set.
Specifically, the preprocessing module 702 includes a fourth processing unit 7024, a fifth processing unit 7025, a calculating unit 7026, and a dimension reducing unit 7027, wherein:
fourth processing unit 7024: the method comprises the steps of performing data enhancement processing on a preprocessed image information set to obtain enhanced image information, wherein the data enhancement processing comprises the steps of manually generating a defect image, affine transformation and color dithering;
fifth processing unit 7025: the method comprises the steps of performing median filtering processing on the enhanced image information to obtain three-dimensional gray image information for removing distortion parts in the enhanced image information;
calculation unit 7026: the three-dimensional gray scale image information is calculated by selecting at least two texture features to obtain feature image information, wherein the texture features comprise roughness, contrast and direction degree;
dimension reduction unit 7027: and the method is used for reducing the dimension of the characteristic image information by utilizing PCA to obtain the defect characteristic of the part image.
Specifically, the building module 703 includes a first obtaining unit 7031, a second obtaining unit 7032, a detecting unit 7033, and a third obtaining unit 7034, wherein:
first obtaining unit 7031: the multi-scale decomposition function is used for obtaining the part image of the shaft sleeve type silk screen gasket according to the part image defect characteristics and the tracking and positioning of the image characteristics;
second obtaining unit 7032: the fusion filtering correlation coefficient of the shaft sleeve type silk screen gasket part image is obtained by adopting a characteristic weight analysis method;
detection unit 7033: the method is used for dynamically detecting the image of the shaft sleeve type wire mesh gasket part by adopting an image super-resolution characteristic reconstruction algorithm based on the scale decomposition function and the fusion filtering correlation coefficient to obtain the polygonal contour characteristic detection frequency of the shaft sleeve type wire mesh gasket part;
third obtaining unit 7034: and the method is used for obtaining texture components according to the polygonal contour feature detection frequency, and further obtaining the defect detection model of the shaft sleeve type silk screen gasket part through the texture components.
Specifically, the identification module 704 includes a splitting unit 7041, a fourth obtaining unit 7042, and an identification unit 7043, wherein:
splitting unit 7041: the image information set of the to-be-detected shaft sleeve type wire mesh gasket is divided into a training set and a testing set based on the defect detection model of the shaft sleeve type wire mesh gasket part, wherein the training set is a defect area characteristic vector of the shaft sleeve type wire mesh gasket part, and the testing set is a damage area characteristic vector of the shaft sleeve type wire mesh gasket part;
fourth obtaining unit 7042: the method comprises the steps of inputting the training set and the testing set into a defect detection model of the shaft sleeve type silk screen gasket part to obtain a first identification result;
identification unit 7043: and training a classification model by using the C4.5 decision tree and the first recognition result, and recognizing to obtain the surface defect of the to-be-detected shaft sleeve type silk screen gasket part.
It should be noted that, regarding the apparatus in the above embodiments, the specific manner in which the respective modules perform the operations has been described in detail in the embodiments regarding the method, and will not be described in detail herein.
Example 3:
corresponding to the above method embodiment, there is further provided a device for detecting surface defects of a wire mesh gasket part of a shaft sleeve, and a device for detecting surface defects of a wire mesh gasket part of a shaft sleeve and a method for detecting surface defects of a wire mesh gasket part of a shaft sleeve described below are referred to in correspondence with each other.
Fig. 3 is a block diagram illustrating a device 800 for detecting surface defects of a wire mesh gasket-like part of a bushing, according to an exemplary embodiment. As shown in fig. 3, the surface defect detecting apparatus 800 of the sleeve-like wire mesh gasket part includes: a processor 801 and a memory 802. The sleeve-like wire mesh gasket part surface defect detection apparatus 800 further includes one or more of a multimedia component 803, an i/O interface 804, and a communication component 805.
The processor 801 is configured to control the overall operation of the apparatus 800 for detecting surface defects of a wire mesh gasket part of a shaft sleeve, so as to complete all or part of the steps in the method for detecting surface defects of a wire mesh gasket part of a shaft sleeve. The memory 802 is used to store various types of data to support the operation of the device 800 for inspecting surface defects of a wire mesh gasket-like part of the bushing, such data may include, for example, instructions for any application or method to operate on the device 800 for inspecting surface defects of a wire mesh gasket-like part of the bushing, as well as application-related data such as contact data, messaging, pictures, audio, video, and the like. The Memory 802 may be implemented by any type or combination of volatile or non-volatile Memory devices, such as static random access Memory (Static Random Access Memory, SRAM for short), electrically erasable programmable Read-Only Memory (Electrically Erasable Programmable Read-Only Memory, EEPROM for short), erasable programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM for short), programmable Read-Only Memory (Programmable Read-Only Memory, PROM for short), read-Only Memory (ROM for short), magnetic Memory, flash Memory, magnetic disk, or optical disk. The multimedia component 803 may include a screen and an audio component. Wherein the screen may be, for example, a touch screen, the audio component being for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 802 or transmitted through the communication component 805. The audio assembly further comprises at least one speaker for outputting audio signals. The I/O interface 804 provides an interface between the processor 801 and other interface modules, which may be a keyboard, mouse, or buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 805 is used for conducting wired or wireless communication between the surface defect detection device 800 of the wire mesh gasket part of the shaft sleeve and other devices. Wireless communication, such as Wi-Fi, bluetooth, near field communication (Near FieldCommunication, NFC for short), 2G, 3G, or 4G, or a combination of one or more thereof, the respective communication component 805 may thus comprise: wi-Fi module, bluetooth module or NFC module.
In an exemplary embodiment, the sleeve-type wire mesh gasket part surface defect detection device 800 may be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, abbreviated as ASIC), digital signal processors (DigitalSignal Processor, abbreviated as DSP), digital signal processing devices (Digital Signal Processing Device, abbreviated as DSPD), programmable logic devices (Programmable Logic Device, abbreviated as PLD), field programmable gate arrays (Field Programmable Gate Array, abbreviated as FPGA), controllers, microcontrollers, microprocessors, or other electronic components for performing the sleeve-type wire mesh gasket part surface defect detection methods described above.
In another exemplary embodiment, a computer readable storage medium is provided that includes program instructions that when executed by a processor perform the steps of the above-described method of surface defect detection of a sleeve-like wire mesh gasket part. For example, the computer readable storage medium may be the memory 802 described above including program instructions executable by the processor 801 of the sleeve-like wire mesh gasket part surface defect detection device 800 to perform the sleeve-like wire mesh gasket part surface defect detection method described above.
Example 4:
corresponding to the above method embodiment, a readable storage medium is further provided in this embodiment, and a readable storage medium described below and a method for detecting a surface defect of a wire mesh gasket part of a shaft sleeve described above may be referred to correspondingly.
The readable storage medium stores a computer program which when executed by a processor realizes the steps of the method for detecting the surface defects of the parts of the shaft sleeve type silk screen gasket in the embodiment of the method.
The readable storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, and the like.
In summary, the invention eliminates the interference of various factors suffered by the image in the industrial environment, and in order to avoid the influence of image noise and shadow on the subsequent extraction of potential defect areas and defect detection, gaussian filtering denoising and image preprocessing are required to be carried out on the acquired surface image of the part; the problem of deficiency of a defective image database is solved through data enhancement, and a normal image is converted into a defective image; increasing the number of defective samples and improving the robustness of the network; the characteristic parameters are reasonably selected according to the defect types, and different parameters are selected according to the surface defects of different study objects, so that the accuracy of the detection result can be effectively improved; the invention ensures the authenticity and reliability of the acquired images, realizes autonomy and intelligence of product detection according to the acquired images, improves detection precision and detection efficiency, promotes the further development of product quality monitoring technology, and performs data identification and matching on various and personalized products so as to improve production efficiency. The invention not only reduces the labor cost, but also improves the detection efficiency of the defects of the parts of the wire mesh gaskets of the shaft sleeves. The false detection rate and the omission rate of the defects of the parts of the wire mesh gaskets of the shaft sleeves are reduced, and the detection accuracy of the defects of the parts of the wire mesh gaskets of the shaft sleeves is further improved.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (4)
1. The method for detecting the surface defects of the shaft sleeve type silk screen gasket part is characterized by comprising the following steps of:
acquiring an image information set of a to-be-detected shaft sleeve type wire mesh gasket, wherein the image information set comprises first image information of the inner surface and second image information of the outer surface of the to-be-detected shaft sleeve type wire mesh gasket, and the first image information and the second image information comprise damage information;
preprocessing the image information set, and extracting texture features of the preprocessed image information set to obtain part image defect features;
constructing a shaft sleeve type silk screen gasket part defect detection model by utilizing the part image defect characteristics;
according to the defect detection model of the parts of the wire mesh gaskets of the shaft sleeves, the shaft sleeves to be detected are detected
The image information set of the silk screen gasket is identified to obtain the surface defect of the part of the silk screen gasket of the shaft sleeve to be detected;
the preprocessing the image information set comprises the following steps:
and carrying out Gaussian noise processing on the image information set by using a Gaussian filtering algorithm to obtain first processed image information, wherein the calculation formula is as follows:
in (1) the->Representing the set of image information, I representing the denoising factor, H representing the gaussian filter, +.>Representing the mean variance of the filtering process,/->Representing first processed image information, T representing time;
normalizing the first processed image information to obtain second processed image information;
performing background reconstruction on the second processed image information by using a polynomial curved surface fitting method to obtain third processed image information, and recording the third processed image information as a preprocessed image information set;
the texture feature extraction is carried out on the preprocessed image information set to obtain part image defect features, wherein the method comprises the following steps:
carrying out data enhancement processing on the preprocessed image information set to obtain enhanced image information, wherein the data enhancement processing process comprises the steps of manually generating a defect image, affine transformation and color dithering;
performing median filtering processing on the enhanced image information to obtain three-dimensional gray image information for removing distortion parts in the enhanced image information;
selecting at least two texture features to calculate the three-dimensional gray image information to obtain feature image information, wherein the texture features comprise roughness, contrast and direction degree;
performing dimension reduction on the feature image information by using PCA to obtain part image defect features;
the method for constructing the defect detection model of the shaft sleeve type silk screen gasket part by utilizing the image defect characteristics of the part comprises the following steps:
obtaining a multiscale decomposition function of the part image of the shaft sleeve type silk screen gasket according to the part image defect characteristics and the tracking and positioning of the image characteristics;
obtaining a fusion filtering correlation coefficient of the shaft sleeve type silk screen gasket part image by adopting a characteristic weight analysis method;
based on the scale decomposition function and the fusion filtering correlation coefficient, adopting an image super-resolution characteristic reconstruction algorithm to dynamically detect the image of the shaft sleeve type wire mesh gasket part to obtain the polygonal contour characteristic detection frequency of the shaft sleeve type wire mesh gasket part;
and obtaining texture components according to the polygonal contour feature detection frequency, and further obtaining the defect detection model of the shaft sleeve type silk screen gasket part through the texture components.
2. The method for detecting surface defects of a shaft sleeve type wire mesh gasket part according to claim 1, wherein the method for performing background reconstruction on the second processed image information by using a polynomial surface fitting method is characterized in that a third processed image information is obtained, the third processed image information is recorded as a preprocessed image information set, and the specific process for performing background reconstruction on target image information by using the polynomial surface fitting method is as follows:
I(x,y)=a 00 +a 10 x+a 01 y+a 20 x 2 +a 02 y 2 +a 30 x 3 +a 03 y 3 +b
in the above formula, I (x, y) is pixel data for reconstructing a background, x, y is coordinate values of pixels for reconstructing a background image, b is an error term, a 00 、a 10 ……a 03 Coefficients corresponding to the polynomials respectively;
and carrying out feature extraction on the third processed image information to obtain a feature extraction image, and recording the feature extraction image as a preprocessed image information set.
3. The utility model provides a axle sleeve class silk screen packing ring part surface defect detection device which characterized in that includes:
the acquisition module is used for: the method comprises the steps of acquiring an image information set of a to-be-detected shaft sleeve type wire mesh gasket, wherein the image information set comprises first image information of the inner surface and second image information of the outer surface of the to-be-detected shaft sleeve type wire mesh gasket, and the first image information and the second image information comprise damage information;
and a pretreatment module: the method comprises the steps of preprocessing an image information set, and extracting texture features of the preprocessed image information set to obtain part image defect features;
the construction module comprises: the method is used for constructing a shaft sleeve type silk screen gasket part defect detection model by utilizing the part image defect characteristics;
and an identification module: the method comprises the steps of identifying the image information set of the shaft sleeve type wire mesh gasket to be detected according to the defect detection model of the shaft sleeve type wire mesh gasket part, and identifying to obtain the surface defect of the shaft sleeve type wire mesh gasket part to be detected;
the preprocessing module comprises:
a first processing unit: the method is used for carrying out Gaussian noise processing on the image information set by utilizing a Gaussian filtering algorithm to obtain first processed image information, and the calculation formula is as follows:
in (1) the->Representing the set of image information, I representing the denoising factor, H representing the gaussian filter, +.>Representing the mean variance of the filtering process,/->Representing first processed image information, T representing time;
a second processing unit: the normalization processing is used for carrying out normalization processing on the first processed image information to obtain second processed image information;
a third processing unit: the method comprises the steps of performing background reconstruction on second processed image information by using a polynomial curved surface fitting method to obtain third processed image information, and recording the third processed image information as a preprocessed image information set;
the preprocessing module comprises:
a fourth processing unit: the method comprises the steps of performing data enhancement processing on a preprocessed image information set to obtain enhanced image information, wherein the data enhancement processing comprises the steps of manually generating a defect image, affine transformation and color dithering;
a fifth processing unit: the method comprises the steps of performing median filtering processing on the enhanced image information to obtain three-dimensional gray image information for removing distortion parts in the enhanced image information;
a calculation unit: the three-dimensional gray scale image information is calculated by selecting at least two texture features to obtain feature image information, wherein the texture features comprise roughness, contrast and direction degree;
dimension reduction unit: the method comprises the steps of performing dimension reduction on the feature image information by utilizing PCA to obtain part image defect features;
the construction module comprises:
a first obtaining unit: the multi-scale decomposition function is used for obtaining the part image of the shaft sleeve type silk screen gasket according to the part image defect characteristics and the tracking and positioning of the image characteristics;
a second obtaining unit: the fusion filtering correlation coefficient of the shaft sleeve type silk screen gasket part image is obtained by adopting a characteristic weight analysis method;
and a detection unit: the method is used for dynamically detecting the image of the shaft sleeve type wire mesh gasket part by adopting an image super-resolution characteristic reconstruction algorithm based on the scale decomposition function and the fusion filtering correlation coefficient to obtain the polygonal contour characteristic detection frequency of the shaft sleeve type wire mesh gasket part;
a third obtaining unit: and the method is used for obtaining texture components according to the polygonal contour feature detection frequency, and further obtaining the defect detection model of the shaft sleeve type silk screen gasket part through the texture components.
4. The surface defect detection device for a wire mesh gasket part of a bushing according to claim 3, wherein the third processing unit performs a specific process of performing background reconstruction on the target image information by using a polynomial surface fitting method, wherein the specific process comprises the following steps:
I(x,y)=a 00 +a 10 x+a 01 y+a 20 x 2 +a 02 y 2 +a 30 x 3 +a 03 y 3 +b
in the above formula, I (x, y) is pixel data for reconstructing a background, x, y is coordinate values of pixels for reconstructing a background image, b is an error term, a 00 、a 10 ……a 03 Coefficients corresponding to the polynomials respectively; and extracting the characteristics of the third processed image information to obtain a characteristic extracted image, and recording the characteristic extracted image as a preprocessed image information set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311234126.0A CN117218097B (en) | 2023-09-23 | 2023-09-23 | Method and device for detecting surface defects of shaft sleeve type silk screen gasket part |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311234126.0A CN117218097B (en) | 2023-09-23 | 2023-09-23 | Method and device for detecting surface defects of shaft sleeve type silk screen gasket part |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117218097A CN117218097A (en) | 2023-12-12 |
| CN117218097B true CN117218097B (en) | 2024-04-12 |
Family
ID=89050796
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311234126.0A Active CN117218097B (en) | 2023-09-23 | 2023-09-23 | Method and device for detecting surface defects of shaft sleeve type silk screen gasket part |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117218097B (en) |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2426069C1 (en) * | 2010-04-01 | 2011-08-10 | Государственное образовательное учреждение высшего профессионального образования "Сибирский государственный индустриальный университет" | Rail surface quality nondestructive examination |
| CN109166111A (en) * | 2018-08-15 | 2019-01-08 | 苏州富鑫林光电科技有限公司 | A kind of electronic ink screen defect inspection method and system |
| CN110826416A (en) * | 2019-10-11 | 2020-02-21 | 佛山科学技术学院 | Bathroom ceramic surface defect detection method and device based on deep learning |
| CN110969620A (en) * | 2019-12-19 | 2020-04-07 | 中国农业大学 | Method and device for detecting magnetic shoe ripple defects |
| CN111105399A (en) * | 2019-12-19 | 2020-05-05 | 苏州经贸职业技术学院 | Switch surface defect detection method and system |
| CN111754454A (en) * | 2020-05-13 | 2020-10-09 | 扬州哈工科创机器人研究院有限公司 | Method and device applied to industrial CT image defect detection |
| CN111968098A (en) * | 2020-08-24 | 2020-11-20 | 广东工业大学 | Strip steel surface defect detection method, device and equipment |
| WO2021146935A1 (en) * | 2020-01-21 | 2021-07-29 | 京东方科技集团股份有限公司 | Image defect determining method and apparatus, and electronic device and storage medium |
| CN114972216A (en) * | 2022-05-10 | 2022-08-30 | 华中科技大学 | Construction method and application of texture surface defect detection model |
| CN114972117A (en) * | 2022-06-30 | 2022-08-30 | 成都理工大学 | Track surface wear identification and classification method and system |
| WO2022227103A1 (en) * | 2021-04-29 | 2022-11-03 | 中奥智能工业研究院(南京)有限公司 | Intelligent detection and mark system and method for parts |
| CN115619743A (en) * | 2022-10-20 | 2023-01-17 | 华中科技大学 | Construction method and application of OLED novel display device surface defect detection model |
| CN116309570A (en) * | 2023-05-18 | 2023-06-23 | 山东亮马新材料科技有限公司 | Titanium alloy bar quality detection method and system |
| CN116721058A (en) * | 2023-05-06 | 2023-09-08 | 新化凯尔影印科技有限公司 | OPC drum surface defect detection method, system, electronic device and storage medium |
| WO2023168972A1 (en) * | 2022-03-09 | 2023-09-14 | 三门三友科技股份有限公司 | Linear array camera-based copper surface defect detection method and apparatus |
| CN116797590A (en) * | 2023-07-03 | 2023-09-22 | 深圳市拓有软件技术有限公司 | Mura defect detection method and system based on machine vision |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114663335A (en) * | 2020-12-22 | 2022-06-24 | 富泰华工业（深圳）有限公司 | Image defect detection method, device, electronic equipment and medium |
-
2023
- 2023-09-23 CN CN202311234126.0A patent/CN117218097B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2426069C1 (en) * | 2010-04-01 | 2011-08-10 | Государственное образовательное учреждение высшего профессионального образования "Сибирский государственный индустриальный университет" | Rail surface quality nondestructive examination |
| CN109166111A (en) * | 2018-08-15 | 2019-01-08 | 苏州富鑫林光电科技有限公司 | A kind of electronic ink screen defect inspection method and system |
| CN110826416A (en) * | 2019-10-11 | 2020-02-21 | 佛山科学技术学院 | Bathroom ceramic surface defect detection method and device based on deep learning |
| CN110969620A (en) * | 2019-12-19 | 2020-04-07 | 中国农业大学 | Method and device for detecting magnetic shoe ripple defects |
| CN111105399A (en) * | 2019-12-19 | 2020-05-05 | 苏州经贸职业技术学院 | Switch surface defect detection method and system |
| WO2021146935A1 (en) * | 2020-01-21 | 2021-07-29 | 京东方科技集团股份有限公司 | Image defect determining method and apparatus, and electronic device and storage medium |
| CN111754454A (en) * | 2020-05-13 | 2020-10-09 | 扬州哈工科创机器人研究院有限公司 | Method and device applied to industrial CT image defect detection |
| CN111968098A (en) * | 2020-08-24 | 2020-11-20 | 广东工业大学 | Strip steel surface defect detection method, device and equipment |
| WO2022227103A1 (en) * | 2021-04-29 | 2022-11-03 | 中奥智能工业研究院(南京)有限公司 | Intelligent detection and mark system and method for parts |
| WO2023168972A1 (en) * | 2022-03-09 | 2023-09-14 | 三门三友科技股份有限公司 | Linear array camera-based copper surface defect detection method and apparatus |
| CN114972216A (en) * | 2022-05-10 | 2022-08-30 | 华中科技大学 | Construction method and application of texture surface defect detection model |
| CN114972117A (en) * | 2022-06-30 | 2022-08-30 | 成都理工大学 | Track surface wear identification and classification method and system |
| CN115619743A (en) * | 2022-10-20 | 2023-01-17 | 华中科技大学 | Construction method and application of OLED novel display device surface defect detection model |
| CN116721058A (en) * | 2023-05-06 | 2023-09-08 | 新化凯尔影印科技有限公司 | OPC drum surface defect detection method, system, electronic device and storage medium |
| CN116309570A (en) * | 2023-05-18 | 2023-06-23 | 山东亮马新材料科技有限公司 | Titanium alloy bar quality detection method and system |
| CN116797590A (en) * | 2023-07-03 | 2023-09-22 | 深圳市拓有软件技术有限公司 | Mura defect detection method and system based on machine vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117218097A (en) | 2023-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110148130B (en) | Method and device for detecting part defects | |
| JP2024509411A (en) | Defect detection method, device and system | |
| US20200402221A1 (en) | Inspection system, image discrimination system, discrimination system, discriminator generation system, and learning data generation device | |
| CN109986172B (en) | Welding seam positioning method, equipment and system | |
| CN110021012B (en) | Mobile phone lens window glass defect detection method based on machine vision technology | |
| JP7170605B2 (en) | Defect inspection device, defect inspection method, and program | |
| WO2022160040A1 (en) | System and method for manufacturing quality control using automated visual inspection | |
| CN115880288B (en) | Detection method, system and computer equipment for electronic element welding | |
| CN115830004A (en) | Surface defect detection method, device, computer equipment and storage medium | |
| CN112381765A (en) | Equipment detection method, device, equipment and storage medium based on artificial intelligence | |
| CN115272336A (en) | Metal part defect accurate detection method based on gradient vector | |
| CN116797590A (en) | Mura defect detection method and system based on machine vision | |
| CN111784645A (en) | Crack detection method for filling pipeline | |
| CN117218097B (en) | Method and device for detecting surface defects of shaft sleeve type silk screen gasket part | |
| CN116051542B (en) | Defect detection method and defect detection device | |
| CN117058089A (en) | Cigarette appearance detection method | |
| CN116381053A (en) | Ultrasonic detection method and system for welding metal materials | |
| CN115239663A (en) | Method and system for detecting defects of contact lens, electronic device and storage medium | |
| CN116977249A (en) | Defect detection method, model training method and device | |
| CN114612434A (en) | Corrugated pipe surface defect detection method and system | |
| CN114283280A (en) | Water surface floating garbage identification method based on improved convolutional neural network | |
| CN107123105A (en) | Images match defect inspection method based on FAST algorithms | |
| CN110147818B (en) | Sparse representation-based laser welding forming defect prediction classification method | |
| CN117392131B (en) | Method and system for detecting defects of inner wall of die casting | |
| CN117593301B (en) | Machine vision-based memory bank damage rapid detection method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |